An extension of the Owen-value interaction index and its application to inter-links prediction

Piotr L. Szczepański, Tomasz P. Michalak, Talal Rahwan, Michael Wooldridge

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Link prediction is a key problem in social network analysis: it involves making suggestions about where to add new links in a network, based solely on the structure of the network. We address a special case of this problem, whereby the new links are supposed to connect different communities in the network; we call it the interlinks prediction problem. This is particularly challenging as there are typically very few links between different communities. To solve this problem, we propose a local node-similarity measure, inspired by the Owen-value interaction index - A concept developed in cooperative game theory and fuzzy systems. Although this index requires an exponential number of operations in the general case, we show that our local node-similarity measure is computable in polynomial time. We apply our measure to solve the inter-links prediction problem in a number of real-life networks, and show that it outperforms all other local similarity measures in the literature.

Original languageEnglish (US)
Title of host publicationFrontiers in Artificial Intelligence and Applications
EditorsGal A. Kaminka, Frank Dignum, Eyke Hullermeier, Paolo Bouquet, Virginia Dignum, Maria Fox, Frank van Harmelen
PublisherIOS Press
Pages90-98
Number of pages9
ISBN (Electronic)9781614996712
DOIs
StatePublished - Jan 1 2016
Event22nd European Conference on Artificial Intelligence, ECAI 2016 - The Hague, Netherlands
Duration: Aug 29 2016Sep 2 2016

Publication series

NameFrontiers in Artificial Intelligence and Applications
Volume285
ISSN (Print)0922-6389

Other

Other22nd European Conference on Artificial Intelligence, ECAI 2016
CountryNetherlands
CityThe Hague
Period8/29/169/2/16

Fingerprint

Game theory
Fuzzy systems
Electric network analysis
Polynomials

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Szczepański, P. L., Michalak, T. P., Rahwan, T., & Wooldridge, M. (2016). An extension of the Owen-value interaction index and its application to inter-links prediction. In G. A. Kaminka, F. Dignum, E. Hullermeier, P. Bouquet, V. Dignum, M. Fox, & F. van Harmelen (Eds.), Frontiers in Artificial Intelligence and Applications (pp. 90-98). (Frontiers in Artificial Intelligence and Applications; Vol. 285). IOS Press. https://doi.org/10.3233/978-1-61499-672-9-90

An extension of the Owen-value interaction index and its application to inter-links prediction. / Szczepański, Piotr L.; Michalak, Tomasz P.; Rahwan, Talal; Wooldridge, Michael.

Frontiers in Artificial Intelligence and Applications. ed. / Gal A. Kaminka; Frank Dignum; Eyke Hullermeier; Paolo Bouquet; Virginia Dignum; Maria Fox; Frank van Harmelen. IOS Press, 2016. p. 90-98 (Frontiers in Artificial Intelligence and Applications; Vol. 285).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Szczepański, PL, Michalak, TP, Rahwan, T & Wooldridge, M 2016, An extension of the Owen-value interaction index and its application to inter-links prediction. in GA Kaminka, F Dignum, E Hullermeier, P Bouquet, V Dignum, M Fox & F van Harmelen (eds), Frontiers in Artificial Intelligence and Applications. Frontiers in Artificial Intelligence and Applications, vol. 285, IOS Press, pp. 90-98, 22nd European Conference on Artificial Intelligence, ECAI 2016, The Hague, Netherlands, 8/29/16. https://doi.org/10.3233/978-1-61499-672-9-90
Szczepański PL, Michalak TP, Rahwan T, Wooldridge M. An extension of the Owen-value interaction index and its application to inter-links prediction. In Kaminka GA, Dignum F, Hullermeier E, Bouquet P, Dignum V, Fox M, van Harmelen F, editors, Frontiers in Artificial Intelligence and Applications. IOS Press. 2016. p. 90-98. (Frontiers in Artificial Intelligence and Applications). https://doi.org/10.3233/978-1-61499-672-9-90
Szczepański, Piotr L. ; Michalak, Tomasz P. ; Rahwan, Talal ; Wooldridge, Michael. / An extension of the Owen-value interaction index and its application to inter-links prediction. Frontiers in Artificial Intelligence and Applications. editor / Gal A. Kaminka ; Frank Dignum ; Eyke Hullermeier ; Paolo Bouquet ; Virginia Dignum ; Maria Fox ; Frank van Harmelen. IOS Press, 2016. pp. 90-98 (Frontiers in Artificial Intelligence and Applications).
@inproceedings{5634ade1be5f4e769599d83cf730af77,
title = "An extension of the Owen-value interaction index and its application to inter-links prediction",
abstract = "Link prediction is a key problem in social network analysis: it involves making suggestions about where to add new links in a network, based solely on the structure of the network. We address a special case of this problem, whereby the new links are supposed to connect different communities in the network; we call it the interlinks prediction problem. This is particularly challenging as there are typically very few links between different communities. To solve this problem, we propose a local node-similarity measure, inspired by the Owen-value interaction index - A concept developed in cooperative game theory and fuzzy systems. Although this index requires an exponential number of operations in the general case, we show that our local node-similarity measure is computable in polynomial time. We apply our measure to solve the inter-links prediction problem in a number of real-life networks, and show that it outperforms all other local similarity measures in the literature.",
author = "Szczepański, {Piotr L.} and Michalak, {Tomasz P.} and Talal Rahwan and Michael Wooldridge",
year = "2016",
month = "1",
day = "1",
doi = "10.3233/978-1-61499-672-9-90",
language = "English (US)",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press",
pages = "90--98",
editor = "Kaminka, {Gal A.} and Frank Dignum and Eyke Hullermeier and Paolo Bouquet and Virginia Dignum and Maria Fox and {van Harmelen}, Frank",
booktitle = "Frontiers in Artificial Intelligence and Applications",

}

TY - GEN

T1 - An extension of the Owen-value interaction index and its application to inter-links prediction

AU - Szczepański, Piotr L.

AU - Michalak, Tomasz P.

AU - Rahwan, Talal

AU - Wooldridge, Michael

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Link prediction is a key problem in social network analysis: it involves making suggestions about where to add new links in a network, based solely on the structure of the network. We address a special case of this problem, whereby the new links are supposed to connect different communities in the network; we call it the interlinks prediction problem. This is particularly challenging as there are typically very few links between different communities. To solve this problem, we propose a local node-similarity measure, inspired by the Owen-value interaction index - A concept developed in cooperative game theory and fuzzy systems. Although this index requires an exponential number of operations in the general case, we show that our local node-similarity measure is computable in polynomial time. We apply our measure to solve the inter-links prediction problem in a number of real-life networks, and show that it outperforms all other local similarity measures in the literature.

AB - Link prediction is a key problem in social network analysis: it involves making suggestions about where to add new links in a network, based solely on the structure of the network. We address a special case of this problem, whereby the new links are supposed to connect different communities in the network; we call it the interlinks prediction problem. This is particularly challenging as there are typically very few links between different communities. To solve this problem, we propose a local node-similarity measure, inspired by the Owen-value interaction index - A concept developed in cooperative game theory and fuzzy systems. Although this index requires an exponential number of operations in the general case, we show that our local node-similarity measure is computable in polynomial time. We apply our measure to solve the inter-links prediction problem in a number of real-life networks, and show that it outperforms all other local similarity measures in the literature.

UR - http://www.scopus.com/inward/record.url?scp=85013029069&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85013029069&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-672-9-90

DO - 10.3233/978-1-61499-672-9-90

M3 - Conference contribution

AN - SCOPUS:85013029069

T3 - Frontiers in Artificial Intelligence and Applications

SP - 90

EP - 98

BT - Frontiers in Artificial Intelligence and Applications

A2 - Kaminka, Gal A.

A2 - Dignum, Frank

A2 - Hullermeier, Eyke

A2 - Bouquet, Paolo

A2 - Dignum, Virginia

A2 - Fox, Maria

A2 - van Harmelen, Frank

PB - IOS Press

ER -